Intel Neural Compute Stick 2

A Plug and Play Development Kit for AI Inferencing
• Build and scale on the Intel Movidius Myriad X Vision Processing Unit (VPU)
• Start developing quickly on Windows 10 or Ubuntu
• Develop on common frameworks and out-of-the-box sample applications
• Operate without cloud compute dependence
• Prototype with low-cost edge devices such as Raspberry Pi 3 and other ARM host devices


Truecasing in natural language processing

Natural language processing (NLP) is the discipline to analyze text data representing records in one of natural languages. Ethnologue.com (21st edition) has data to indicate that of the currently listed 7,111 living languages, 3,995 have a developed writing system (such as English, French, Yemba, Chinese, …). NLP applications include text categorization, spelling & grammar correction, information extraction, speech recognition, machine translation, text to speech synthesis, synonym generation, as well as more advanced domains such as summarization, question answering, dialog systems and speech imitation. In this post, we review existing approaches in solving Truecasing on a practical example. Truecasing is a NLP problem of finding the proper capitalization of words within a text where such information is unavailable. Truecasing aids in NLP tasks, such as named entity recognition, automatic content extraction, and machine translation. Proper capitalization enables easier detection of proper nouns, and helps increasing accuracy in translation.


Moore’s law is dead

We are accustomed to thinking that computer speed doubles every 18 months as predicted by Moore’s law. Indeed for the past 50 years that was the case. However Moore’s law is coming to an end due to technical obstacles. What alternatives do we have?


Why you should avoid removing STOPWORDS

You might think it is very common to remove stop words from text during prepocessing it. Yes, I agree with you but you should be careful about what kind of stopwords you are removing. The most common method to remove stop words is using NLTK’s stopwords. Let’s look at the list of stop words from nltk.


Machine Learning with One Line of Code!

Machine Learning libraries are getting easier and easier to work with. Their objective is to hide complex mathematical operations and offer simple APIs. Recently, I stumbled upon MindsDb. A new platform that enables users to train models with only one line of code! I know it sounds a little bit exaggerated but follow me and you will see.


A Comprehensive Guide to Natural Language Generation

As long as Artificial Intelligence helps us to get more out of the natural language, we see more tasks and fields mushrooming at the intersection of AI and linguistics. In one of our previous articles, we discussed the difference between Natural Language Processing and Natural Language Understanding. Both fields, however, have natural languages as input. At the same time, the urge to establish two-way communication with computers has lead to the emergence of a separate subcategory of tasks dealing with producing (quasi)-natural speech. This subcategory, called Natural Language Generation will be the focus of this blog post.